SEHH2031 Statistics Exercises for Chapter 08

SEHH2031 Statistics - Chapter 08

Tutorial Exercises
(Correct the final answers to 4 decimal places whenever appropriate.)
Use the Tables to answer the questions.

1. A random sample of 40 engineers was selected from among the large number employed
by a corporation engaged in seeking new sources of petroleum. The hours worked in a
particular week were determined for each engineer selected. These data had a mean of
46 hours and a standard deviation of 3 hours. For that particular week, estimate the mean
hours worked for all engineers in the corporation with 95% confidence.

2. The breaking strength of threads is follow normal distribution with a standard deviation
of 18 grams. How many measures on breaking strength should be used in the next
experiment if the estimate of the true mean breaking strength is to be within 4 grams with
90% confidence?

3. A local environmental authority has collected data on the LC50 (concentration killing 50%
of the test animals in a specified time interval) measurements for certain chemicals likely
to be found in freshwater rivers and lakes. For a certain species of fish, the LC50
measurements (in parts per million) for DDT in 12 experiments yielded the following :

16, 5, 21, 19, 10, 5, 8, 2, 7, 2, 4, 9

Assuming such LC50 measurements to be approximately normally distributed, estimate

the true mean LC50 for DDT with 90% confidence.

4. A research studied the fatigue behavior of reinforced concrete beams in seawater.

Assuming the number of cycles to failure in seawater for beams subjected to certain
bending and loading stress is normally distributed and listed as follows (in thousands):

774, 633, 477, 268, 407, 576, 659, 963, 193

(a) Construct a 90% confidence interval estimate for the average number of cycles to
failure for beams of this type.
(b) What is the minimum additional number of sample required so that the estimated
average number of cycles to failure for beams to within 40,000 of the true value with
95% confidence?

5. A random sample of 25 working women yielded a sample mean income of $45,000.

Assume that the population standard deviation is $6,000 and that the distribution of such
incomes is normal.

(a) Construct and interpret a 99% confidence interval for the mean income of the
population of all working women.
(b) What is the minimum sample size required if we want to estimate the population
mean, with 95% confidence, to within $1,000 of the true value.

Page 1
SEHH2031 Statistics Exercises for Chapter 08

6. A random sample of 45 children showed a mean increase of 7 IQ points after listening to

a Mozart piano sonata for about 10 minutes. The distribution of such increases is
unknown, but the standard deviation is assumed to be 2 IQ points. Construct and
interpret a 95% confidence interval for the mean increase in IQ points after listening to a
Mozart piano sonata.

7. The Health Department is interested in estimating the population mean number of

cigarettes smoked per capita in order to evaluate the efficacy of the antismoking
campaign. A random sample of 8 cities throughout the country yielded the following
numbers of cigarettes smoked annually per capita: (Assume the data are normally
distributed)

2,206 2,990 2,540 2,116 2,010 2,791 2,392 2,692

Construct a 95% confidence interval for the population mean per capita number of
cigarettes smoked.

8. A random sample of 75 parking metres collected a mean of $120 per metre with a
standard deviation of $30. Construct and interpret a 90% confidence interval for the
population mean amount of money collected by all parking metres.

Page 2
SEHH2031 Statistics Exercises for Chapter 08

Supplementary Exercises
(Correct the final answers to 4 decimal places whenever appropriate.)
Use the Tables to answer the questions.

1. A sample of 31 data observations has a sample mean of 53.42 and a sample standard
deviation of 3.05.
(a) Construct a 95% confidence interval for the true mean.
(b) How many additional data observations should be obtained so that we are 95%
confident that the estimated sample mean will be within 1.0 of the true mean?

2. A random sample of 41 glass sheets is obtained and their thicknesses are measured.
The sample mean is 3.04 mm and the sample standard deviation is 0.124 mm.
(a) Construct a 99% confidence interval for the true mean glass sheet thickness.
Do you think it is plausible that the mean glass thickness is 2.90 mm?
(b) How many additional glass sheets should be sample to construct a 99%
confidence interval for the true mean sheet thickness with a length no wider
than 0.05 mm?

3. The breaking strengths of a random sample of 20 bundles of wool fibres have a sample
mean of 436.5 and a sample standard deviation of 11.90. (Assume the breaking
strengths of bundles of wool fibres are normally distributed)
(a) Construct 90%, 95%, and 99% confidence intervals for the true average
breaking strength. Compare the lengths of the confidence intervals. Do you
think it is plausible that the average breaking strength is equal to 450.0?
(b) How many additional data observations should be obtained to construct a 99%
confidence interval for the average breaking strength with a length no wider
than 10.0?

4. A random sample of 16 one-kg sugar packets is obtained and the actual weights of the
packets are measured. The sample mean is 1.053 kg and the sample standard
deviation is 0.058 kg. (Assume the weights of the sugar packets are normally
distributed) Construct a 99% confidence interval for the true average sugar packet
weight. Do you think it is plausible that the average weight is 1.025 kg?

5. A sample of 28 data observations has a sample mean of 0.0328. Suppose the

distribution is normal with population standard deviation is known to be 0.015,
construct a 95% confidence interval for the true mean.

6. A boot manufacturer is testing the quality of leather provided by a potential supplier.

The manufacturer wants to construct a confidence interval with a confidence level of
95% that has a length no wider than 0.1, and from previous experience it is believed
that the variability in the leather is such that the standard deviation is no wider than
0.2031. What sample size would you recommend?

7. An experimenter feels that a population standard deviation is no wider than 10.0 and
would like to construct a 95% confidence interval for the population mean that has a
length at most 5.0. What sample size would you recommend?

Page 3
SEHH2031 Statistics Exercises for Chapter 08

8. Assume the following data set was selected from a normal population. Construct a
99% confidence interval for the population mean.
34, 45, 27, 33, 38, 41, 45, 29, 30, 39, 34, 40, 28, 33, 36

9. The pH levels of a random sample of 16 chemical mixtures from a process were

measured. Sample mean of 6.861 and a sample standard deviation of 0.440 were
obtained. The scientists presented a confidence interval (6.668, 7.054) for the average
pH level of chemical mixtures from the process. What is the confidence level of this
confidence interval? (Assume the pH levels of the chemical mixtures are normally
distributed)

10. Chilled cast iron is used for mechanical components that need particularly high levels
of hardness and durability. In an experiment to investigate the corrosion properties
of a particular type of chilled cast iron, a collection of n = 10 samples of this chilled
cast iron provided corrosion rates with a sample mean of 2.752 and a sample standard
deviation of 0.280. Construct a 99% confidence interval for the true average corrosion
rate for chilled cast iron of this type. (Assume the corrosion rates are normally
distributed) Is 3.1 a plausible value for the average corrosion rate?

11. An experiment would like to construct a 99% confidence interval, with a length at most
0.2 ohms, for the average resistance of a segment of copper cable of a certain length.
If the experimenter feels that the standard deviation of such resistances is no wider
than 0.15 ohms, what sample size would you recommend?

12. A random sample of 14 chemical solutions is obtained and their strengths are
measured. The sample mean is 5437.2 and the sample standard deviation is 376.9.
(Assume the strengths of the chemical solutions are normally distributed)
(a) Construct a 95% confidence interval for the true average strength.
(b) Estimate how many additional chemical solutions need to be measured in
order to obtain a 95% confidence interval for the true average strength with a
length no larger than 300 assume population standard deviation is also equal
to 376.9.

13. The resilient moduli of 10 samples of a clay mixture are measured and the sample
mean is 19.50. Suppose the population standard deviation of the resilient modulus is
known to be 1.0, construct the 90%, 95%, and 99% confidence intervals for the true
average resilient modulus. Compare the lengths of the confidence intervals. Do you
think it is plausible that the average resilient modulus is equal to 20.0?

14. The breaking strengths of a random sample of 26 moulded plastic housings were
measured. A sample mean of 479.42 and a sample standard deviation of 12.55 were
obtained. A confidence interval (472.56, 486.28) for the average strength of moulded
plastic housings was constructed from these results. What is the confidence level of
this confidence interval? (Assume the breaking strengths of the moulded plastic
housings are normally distributed)

Page 4
SEHH2031 Statistics Exercises for Chapter 08

15. For a random sample of 50 measurements on the breaking strength of cotton threads,
the mean breaking strength was found to be 210 g and the standard deviation 18 g.
Construct a confidence interval for the true mean breaking strength of cotton threads
of this type with 90% confidence.

16. An important property of plastic clays is the per cent of shrinkage on drying. For a
certain type of plastic clay, 45 test specimens showed an average shrinkage
percentage of 18.4 and a standard deviation of 1.2. How many more specimens
should be tested if it is desired to estimate the per cent of shrinkage to within 0.2 with
98% confidence?

17. The warp wise breaking strength measured on five specimens of a certain cloth gave
a sample mean of 180 psi and a standard deviation of 5 psi.
(a) Estimate the true mean warp wise breaking strength for cloth of this type in a
95% confidence interval.
(b) What assumption is necessary for your answer to be valid?

18. Fifteen resistors were randomly selected from the output of a process supposedly
producing 10-ohm resistors. The 15 resistors actually showed a sample mean of 9.8
ohms and a sample standard deviation of 0.5 ohm. Find a 95% confidence interval for
the true mean resistance of the resistors produced by this process. (Assume
resistance measurements are approximately normally distributed.)

19. The increased use of wood for residential heating has caused some concern over the
pollutants and irritants released into the air. In one reported study, the total
suspended particulates (TSP) in nine air samples had a mean of 72 µg/m3 and a
standard deviation of 23. Estimate the true mean TSP in a 95% confidence interval.
What assumption is necessary for your answer to be valid?

20. The diameter measurements of an armoured electric cable, taken at 10 points along
the cable, yield a sample mean of 2.1 cm and a sample standard deviation of 0.3 cm.
(a) Estimate the average diameter of the cable in a confidence interval with 90%
confidence. What assumptions are necessary for your answer to be valid?
(b) Suppose the sample mean and standard deviation had come from a sample of
100 measurements. Construct a 90% confidence interval for the true average
diameter of the cable. What assumption must necessarily be made?

21. The hardness measure of steel ingots is produced by pressing a diamond point into
the steel and measuring the depth of penetration. A sample of 15 hardness
measurements on specimens of steel gave a sample mean of 65 and a sample variance
of 90. Estimate the true mean hardness in a 95% confidence interval, assuming the
measurements to come from a normal distribution.

22. Window sizes in integrated circuit chips must be of fairly uniform size in order for the
circuits to function properly. Thus, the variance of the window width measurements
is an important quantity. The following is a set of window widths data on a sample of
10 test locations (in µm).

Page 5
SEHH2031 Statistics Exercises for Chapter 08

2.52, 2.50, 2.66, 2.73, 2.71, 2.67, 2.06, 1.66, 1.78, 2.56
Estimate the average window width in a 95% confidence interval.

23. A certain type of wire is manufactured in large rolls. A quality check required five
specimens from a roll to be tested for the tensile strength. The measurements (in
1,000 psi) turned out to be 253, 261, 258, 255, and 256. Use these data to construct
a 95% confidence interval estimate of the true mean tensile strength.

24. In a study of the amount of lead element in drinking water undertaken, the same
standard was run through the laboratory six times at random intervals. The six
readings (in parts per million [ppm]) were as follows:
9.54 9.61 9.32 9.48 9.70 9.26
(a) Assume the readings were taken from a normal population, construct a 95%
confidence interval for the true average amount of lead in drinking water.
(b) Suppose the true average and standard deviation of amount of lead readings
from the experiment is known to be 9.50 ppm and 0.345 ppm respectively. How
many more additional readings should be collected so that we are 90% confident
to claim that the sample mean amount of lead will be within 0.08 ppm of the true
amount in the drinking water?

25. A machine is producing metal pieces that are cylindrical in shape. A sample of these
metal pieces is taken and the diameters (in cm) are as follows.
1.01 0.97 1.03 1.04 0.99 0.98 0.99 1.01 1.03
Assume the diameters of metal pieces are normally distributed.
(a) Find a 99% confidence interval for the true mean diameter of metal pieces from
this machine.
(b) Suppose the manger wants to estimate the mean diameter of metal pieces within
0.25 cm of its true value with a 95% confidence, what is the minimum number of
additional samples required to achieve this level of accuracy given that its
population standard deviation is 0.55 cm?

26. It is known that the weights of fishes in a certain pond are normally distributed. Suppose
a random sample of 25 fishes is caught from this pond and the corresponding sample
mean weight is found to be 3,200 grams with a sample standard deviation of 500 grams.
(a) Construct a 90% confidence interval for the true mean fish weight in this pond.
(b) Suppose you want to estimate true mean within 50 grams with 94% level of
confidence, what is the minimum sample size required?

27. The pH levels of a random sample of 10 bottles of a certain type of chemical mixtures
are measured and summarised as follows:
2.7 2.9 3.4 4.6 5.2 5.8 6.7 6.8 7.9 8.2

Assume that the pH level of this type of chemical mixture is normally distributed.
Construct a 98% confidence interval for the true mean pH levels of this type of
chemical mixture.

28. A bus manufacturer wants to estimate the true mean and variance of fuel

Page 6
SEHH2031 Statistics Exercises for Chapter 08

consumption (in litre per kilometre) for its model X bus. A random sample of 15
buses of this model was tested and produced the following data concerning their
fuel consumption (in litre per kilometre). Assume that the fuel consumption for all
such buses is normally distributed.
12.5 13.4 11.2 12.8 11.8 12.7 14.3 14.1
11.3 12.6 13.8 13.3 13.6 15.0 12.6
(a) Construct a 90% confidence interval for the population mean fuel consumption
of model X bus.
(b) What is the minimum sample size required so that the estimated mean fuel
consumption of model X buses will be within 0.12 of its true value with a 99%
confidence?

30. The following data represent the monthly expenditure on daily travel for 10 randomly
selected working adult from a low income family:
$300 $330 $350 $380 $430 $450 $460 $510 $600 $650
(a) Find a 90% confidence interval for the mean monthly expenditure on daily travel
for working adult from a low income family.
(b) Assume the population standard deviation is known. If one increases the
confidence level while keeping the same sample size, what is the effect on the
length of a confidence interval of a population mean?

31. The following data represent the daily expenditure on lunch (in dollars) for 10
randomly selected secondary school students:
15.0 16.5 17.5 19.0 21.5 22.5 23.0 25.5 30.0 32.5
(a) Find a 90% confidence interval for the mean daily expenditure on lunch for
secondary school students.
(b) Assume the population variance is 5 (dollars)2. Construct a 98% confidence
interval for the mean daily expenditure on lunch for secondary school students.
(c) Assume the population standard deviation is known. If one increases the
confidence level while keeping the same sample size, what is the effect on the
length of a confidence interval of a population mean?
(d) Assume the population standard deviation is known. If one increases the sample
size while keeping the same confidence level, what is the effect on the length of
a confidence interval of a population mean?

32. Water Supplies Department tests the drinking water of homeowners for
contaminants such as lead and iron. The lead and iron levels in water specimens
collected for a sample of 13 residents are shown in the following table.
Lead 1.32 0 1.31 0.92 0.66 3 1.32
(mg/L) 4.09 4.45 0 3.21 0.88 2.32
Iron 0.485 0.222 0.875 0.508 0.904 0.221 0.283
(mg/L) 0.475 0.13 0.22 0.743 0.279 0.32
Suppose that population standard deviation of iron level is 0.24 mg/L.
(a) Construct a 99% confidence interval for the mean lead level in water specimens.
(b) Interpret the interval obtained in (a), in the context of this problem.
(c) Construct a 95% confidence interval for the mean iron level in water specimens.

Page 7
SEHH2031 Statistics Exercises for Chapter 08

(d) For quality control purposes, we wish to estimate the mean iron level in water
specimens to within 0.025 mg/L of its true value with a 98% confidence interval.
What sample size should be used?

33. The manager of a company wants to investigate the job satisfaction of the staff. He
believes that one of the major concerns of the staff is the family life. A random
sample of 36 married staff of the company revealed that the mean weekly amount
of time (in hours) they spent on taking care for their children was 28.3 hours, with a
standard deviation of 12.3 hours.
(a) Construct a 95% confidence interval for the mean number of hours that married
staff spent on taking care for their children.
(b) If the director wants his estimate of the mean number of hours that married staff
spent on taking care of their children to be within ±2 hours, with 98% level of
confidence, how large a sample is required?

Page 8